{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Age Gender to CSV for Site"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%reload_ext autoreload\n",
    "%autoreload 2\n",
    "\n",
    "import os\n",
    "from os.path import join\n",
    "import math\n",
    "import time\n",
    "from glob import glob\n",
    "import datetime\n",
    "from collections import OrderedDict\n",
    "from operator import itemgetter\n",
    "from datetime import datetime\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from pathlib import Path\n",
    "from tqdm import tqdm_notebook as tqdm\n",
    "import imutils\n",
    "import random\n",
    "%matplotlib inline\n",
    "import matplotlib.pyplot as plt\n",
    "import random\n",
    "\n",
    "import sys\n",
    "sys.path.append('/work/megapixels_dev/megapixels')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [],
   "source": [
    "dk = 'helen'\n",
    "fp_in = '/data_store_hdd/datasets/people/helen/metadata/face_attributes.csv'\n",
    "fp_out_age = f'/work/megapixels_dev/site/content/pages/datasets/{dk}/assets/age.csv'\n",
    "fp_out_gender = f'/work/megapixels_dev/site/content/pages/datasets/{dk}/assets/gender.csv'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(fp_in)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Age\n",
    "results = []\n",
    "brackets = [(0, 12), (13, 18), (19,24), (25, 34), (35, 44), (45, 54), (55, 64), (64, 75), (75, 100)]\n",
    "df_age = df['age_real']\n",
    "\n",
    "for a1, a2 in brackets:\n",
    "  n = len(df_age.loc[((df_age >= a1) & (df_age <= a2))])\n",
    "  results.append({'age': f'{a1} - {a2}', 'faces': n})\n",
    "  \n",
    "df_out = pd.DataFrame.from_dict(results)\n",
    "df_out = df_out[['age','faces']]\n",
    "df_out.to_csv(fp_out_age, index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Gender\n",
    "results = []\n",
    "\n",
    "df_f = df['f']\n",
    "nm = len(df_f.loc[((df_f < 0.33))])\n",
    "nnb = len(df_f.loc[((df_f >= 0.33) & (df_f <= 0.66))])\n",
    "nf = len(df_f.loc[((df_f > 0.66))])\n",
    "\n",
    "results = []\n",
    "results.append({'gender': 'male', 'faces':nm})\n",
    "results.append({'gender': 'female', 'faces': nf})\n",
    "results.append({'gender': 'they', 'faces': nnb})\n",
    "\n",
    "df_out = pd.DataFrame.from_dict(results)\n",
    "df_out = df_out[['gender','faces']]\n",
    "df_out.to_csv(fp_out_gender, index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "megapixels",
   "language": "python",
   "name": "megapixels"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}